Previous studies regarding transportation impacts on economic development in urban areas have three major issues—the limited scope of analysis mostly with the change of property values, the exclusion of smart transportation systems as features despite their potential for urban areas, and stereotyped approaches with limited types of variables. To surmount such limitations, this research adopted the concept of Big Data with machine learning techniques. As such, a total of 67 features from main categories, including the change of business, geographical boundary, socio-economic, land value, transportation, smart transportation, sales, and floating population were analyzed with XGBoost and SHAP algorithms. Given that the rise and fall of business is a major consideration for economic development in urban areas, the change in the total number of sales was selected as a target value. As a result, sales-related features showed the largest contribution to the rise of business, among others. It was also noted that features related to smart transportation systems obviously affected the success of business, even more than traditional ones from transportation. It is thus expected that the findings from this research will provide insights for decision-makers and researchers to make customized policies for boosting economic development in urban areas that are a major part of the urban economy to achieve sustainability.

Aggregation of spatiotemporal data can encounter potential information loss or distort attributes via individual observation, which would influence modeling results and lead to an erroneous inference, named the ecological fallacy. Therefore, deciding spatial and temporal resolution is a fundamental consideration in a spatiotemporal analysis. The modifiable temporal unit problem (MTUP) occurs when using data that is temporally aggregated. While consideration of the spatial dimension has been increasingly studied, the counterpart, a temporal unit, is rarely considered, particularly in the traffic safety modeling field. The purpose of this research is to identify the MTUP effect in crash-frequency modeling using data with various temporal scales. A sensitivity analysis framework is adopted with four negative binomial regression models and four random effect negative binomial models having yearly, quarterly, monthly, and weekly temporal units. As the different temporal unit was applied, the result of the model estimation also changed in terms of the mean and significance of the parameter estimates. Increasing temporal correlation due to using the small temporal unit can be handled with the random effect models.